In this paper we analyse the problem of generating referring expressions in a multilingnal generation system that produces instructions on how to fill out pension forms. The model...
Approximate text search is a basic technique to handle recognized text that contains recognition errors. This paper proposes an approximate string search for recognized text using...
We propose a new image and blur prior model, based on nonstationary autoregressive (AR) models, and use these to blindly deconvolve blurred photographic images, using the Gibbs sa...
— We suggest a new navigation approach to mobile robots, within a nonlinear model predictive control framework where a navigation function is used as a control Lyapunov function....
In natural language processing, ambiguity resolution is a central issue, and can be regarded as a preference assignment problem. In this paper, a Generalized Probabilistic Semanti...